Showing 2025Show all
2 papers · 1 filter
eess.SY2025
Efficient Discovery of Actual Causality in Stochastic Systems
Arshia Rafieioskouei, Kenneth Rogale, Borzoo Bonakdarpour
Identifying the actual cause of events in engineered systems is a fundamental challenge in system analysis. Finding such causes becomes more challenging in the presence of noise an…
cs.AI2025
HypRL: Reinforcement Learning of Control Policies for Hyperproperties
Tzu-Han Hsu, Arshia Rafieioskouei, Borzoo Bonakdarpour
Reward shaping in multi-agent reinforcement learning (MARL) for complex tasks remains a significant challenge. Existing approaches often fail to find optimal solutions or cannot ef…